RobustSora benchmark demonstrates that current AI video detectors rely heavily on visible watermarks, with average accuracy drops of 6.6 percentage points when watermarks are erased and increased false alarms when watermarks are spoofed onto real videos.
hub
Ultravideo: High-quality uhd video dataset with comprehensive captions
14 Pith papers cite this work. Polarity classification is still indexing.
14
Pith papers citing it
hub tools
citation-role summary
dataset 2
citation-polarity summary
fields
cs.CV 14roles
dataset 2representative citing papers
VINS-120K supplies the first large-scale set of instruction-image-edited-image triplets at ultra-high resolution together with an adaptation strategy that improves detail synthesis.
SmartDirector generates cinematic videos via Director-Gen for low-res keyframe-conditioned output followed by Director-SR refinement using high-res keyframes, trained on curated movie sequences.
AtlasVid proposes a decoupled global-local diffusion framework that trains at low resolution with LoRA and generalizes to ultra-high-resolution long video synthesis via semantic proxy guidance and locality-preserving attention.
SwiftI2V achieves comparable 2K I2V quality to end-to-end models on VBench-I2V while cutting GPU time by 202x through low-resolution motion planning followed by strongly image-conditioned segment-wise high-resolution synthesis.
CHAI framework pairs AI pre-captions with expert human critiques to produce precise video descriptions, enabling open models to outperform closed ones like Gemini-3.1-Pro and improve fine-grained control in video generation models.
SVOR achieves stable, shadow-free video object removal under real-world imperfections via MUSE mask handling, DA-Seg localization, and curriculum training on real and synthetic data.
MoVA introduces modular asymmetric dual projections to handle temporal misalignment and semantic asymmetry in long video-text alignment.
Generated video latents are pushed toward a shell-shaped manifold fitted to high-quality SFT video patches, producing a dense reward that reduces blur, over-smoothing, and motion artifacts in text-to-video models.
A decoupled-control autoregressive video model using Fast-Slow Memory training, dynamic projection, and staged camera control to produce stable long-horizon outputs with human and viewpoint guidance.
Introduces CineDance-1M dataset for multi-shot long-form text-to-audio-video generation along with CineBench and a model adaptation.
Ultra Flash introduces a cascaded streaming super-resolution framework with specialized training, upsampling, and optimization to enable real-time high-resolution video generation from low-res diffusion models.
ByG enables unpaired training of flow matching editing models by pairing self-extracted instruction-following cues with cycle-consistency and routing gradients from clean predictions to noisy states.
PixVerve introduces a 95K ultra-high-resolution image-text dataset and training strategies that enable native 100-megapixel text-to-image generation together with a new evaluation benchmark.
citing papers explorer
-
RobustSora: De-Watermarked Benchmark for Robust AI-Generated Video Detection
RobustSora benchmark demonstrates that current AI video detectors rely heavily on visible watermarks, with average accuracy drops of 6.6 percentage points when watermarks are erased and increased false alarms when watermarks are spoofed onto real videos.
-
VINS-120K: Ultra High-Resolution Image Editing with A Large-Scale Dataset
VINS-120K supplies the first large-scale set of instruction-image-edited-image triplets at ultra-high resolution together with an adaptation strategy that improves detail synthesis.
-
SmartDirector: Keyframe-Conditioned Cinematic Video Generation with Narrative Pacing Control
SmartDirector generates cinematic videos via Director-Gen for low-res keyframe-conditioned output followed by Director-SR refinement using high-res keyframes, trained on curated movie sequences.
-
AtlasVid: Efficient Ultra-High-Resolution Long Video Generation via Decoupled Global-Local Modeling
AtlasVid proposes a decoupled global-local diffusion framework that trains at low resolution with LoRA and generalizes to ultra-high-resolution long video synthesis via semantic proxy guidance and locality-preserving attention.
-
SwiftI2V: Efficient High-Resolution Image-to-Video Generation via Conditional Segment-wise Generation
SwiftI2V achieves comparable 2K I2V quality to end-to-end models on VBench-I2V while cutting GPU time by 202x through low-resolution motion planning followed by strongly image-conditioned segment-wise high-resolution synthesis.
-
Building a Precise Video Language with Human-AI Oversight
CHAI framework pairs AI pre-captions with expert human critiques to produce precise video descriptions, enabling open models to outperform closed ones like Gemini-3.1-Pro and improve fine-grained control in video generation models.
-
From Ideal to Real: Stable Video Object Removal under Imperfect Conditions
SVOR achieves stable, shadow-free video object removal under real-world imperfections via MUSE mask handling, DA-Seg localization, and curriculum training on real and synthetic data.
-
MoVA: Learning Asymmetric Dual Projections for Modular Long Video-Text Alignment
MoVA introduces modular asymmetric dual projections to handle temporal misalignment and semantic asymmetry in long video-text alignment.
-
Your Data Manifold is Secretly a Reward Model: Shell-LCC for Text-to-Video Generation
Generated video latents are pushed toward a shell-shaped manifold fitted to high-quality SFT video patches, producing a dense reward that reduces blur, over-smoothing, and motion artifacts in text-to-video models.
-
Directing the World: Fast Autoregressive Video Generation with Compositional Human-Camera Control
A decoupled-control autoregressive video model using Fast-Slow Memory training, dynamic projection, and staged camera control to produce stable long-horizon outputs with human and viewpoint guidance.
-
CineDance: Towards Next-Generation Multi-Shot Long-Form Cinematic Audio-Video Generation
Introduces CineDance-1M dataset for multi-shot long-form text-to-audio-video generation along with CineBench and a model adaptation.
-
Ultra Flash: Scaling Real-Time Streaming Video Generation to High Resolutions
Ultra Flash introduces a cascaded streaming super-resolution framework with specialized training, upsampling, and optimization to enable real-time high-resolution video generation from low-res diffusion models.
-
Bootstrap Your Generator: Unpaired Visual Editing with Flow Matching
ByG enables unpaired training of flow matching editing models by pairing self-extracted instruction-following cues with cycle-consistency and routing gradients from clean predictions to noisy states.
-
PixVerve: Advancing Native UHR Image Generation to 100MP with a Large-Scale High-Quality Dataset
PixVerve introduces a 95K ultra-high-resolution image-text dataset and training strategies that enable native 100-megapixel text-to-image generation together with a new evaluation benchmark.